SpatioTemporalSegmentation-ScanNet icon indicating copy to clipboard operation
SpatioTemporalSegmentation-ScanNet copied to clipboard

can't run your code

Open slcheng97 opened this issue 3 years ago • 0 comments

When I try to run your code, I meet the follwing bugs:

Traceback (most recent call last): File "main.py", line 158, in main() File "main.py", line 151, in main train(model, train_data_loader, val_data_loader, config) File "/home/slcheng/code/SpatioTemporalSegmentation-ScanNet-0.5/lib/train.py", line 103, in train loss = criterion(sliced_output, target.long()) File "/home/slcheng/anaconda3/envs/pt17/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/slcheng/anaconda3/envs/pt17/lib/python3.7/site-packages/torch/nn/modules/loss.py", line 962, in forward ignore_index=self.ignore_index, reduction=self.reduction) File "/home/slcheng/anaconda3/envs/pt17/lib/python3.7/site-packages/torch/nn/functional.py", line 2468, in cross_entropy return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction) File "/home/slcheng/anaconda3/envs/pt17/lib/python3.7/site-packages/torch/nn/functional.py", line 1605, in log_softmax ret = input.log_softmax(dim) AttributeError: 'TensorField' object has no attribute 'log_softmax'

Any reasons why I get this error?

slcheng97 avatar Dec 16 '21 08:12 slcheng97